Automation

Jev gates Bash, Write and Edit, and screens Read and Bash results for injected instructions; a blocked command is held, for the person to run anyway or keep blocked

Redacts secrets and PII from every row Claude Code stores, before the model reads it and before the transcript keeps it. Reach L0: no network, no processes, no files.

Enforce the style rules Claude keeps ignoring: banned words and phrases, a comment-density cap on added code, and files that must not gain comments. Rules live in .claude/style-cop.md and are both shown to Claude and enforced on edits.

Asks before harsh DevOps commands: destructive Docker, Kubernetes and Helm calls, CI config edits, broad chmod and chown, and git commands that lose work. Add infra-guard for plain kubectl delete.

Asks before a live API key, token or private key is written, edited or run.

reads every Bash call, fork spawn and Write before it runs: a Write over a tracked file the session never read, a floor command, a system, overwrite, prune or remote-delete command, a known hazard shape, a coder spawn whose brief has no x brief check stamp, or a fork with no why-fork line is refused with its safe door, never a dialog; each refusal and escape is kept in its own store as an...

Logs every function-hook event (on '*') to JSONL for inspection.

The learning loop: every main turn is kept in a ledger across sessions (phase, effort, steps, failed tool calls, agents, advisor calls), joined with the outcomes observed at tool.call (commits kept or reverted, test exits, PR verdicts and merges, no transcript) and the ones /insights writes, and the project's goals; probe sessions are counted and kept out; a phase whose evidence, read on the...

Läuft ein Testbefehl grün durch und liegen danach uncommittete Änderungen im Repo, bekommt Claude still einen Hinweis, den Arbeitsschritt zu committen. Keine Dauerabfrage, kein Git-Hook.

Shows the state of Claude (working, permission, input, idle, background, compacting) in the iTerm2 tab subtitle.

Sends each local session's status (what Claude is doing, task progress, context and usage) to the Claude Widget desktop app on this computer, and takes its Stop button

Rules for Claude Code alerts: when one is worth sending (done, blocked, error, usage limits) and where it goes (chime, macOS notification, ntfy, Slack, Discord or a JSON webhook).

The Loadout's core work board and orchestration loop for Claude Code. Tickets are classified into categories that route each one to a concrete model and effort, then dispatched to token-gated executors; side issues you mention mid-task get captured on the spot, and a live, self-hosted Kanban dashboard spans every project you work in.

Counts every skill expansion (typed /name, the Skill tool, a preload) in the plugin store, across sessions; /skill-usage shows the table. Observe-only: never changes what the model reads. No files, no network. English by default, Russian by a one-line switch.

Reports what a Claude Code session is really doing (idle / working / tool / permission, plus signals and token use) from inside the session, as a JSON snapshot and a JSONL event log

Vigia de API paga: pergunta antes de ferramentas e comandos que gastam dinheiro ou créditos (Magnific, Kling, HeyGen, OpenRouter, Groq...), com autorização por 1 hora (/vigia, /vigia limpar)

Protects the Sparkle EdDSA signing key: denies deleting it from the keychain, asks before generate_keys may create or import a key and before an edit changes an existing SUPublicEDKey